Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- extended-abstractOctober 2024
RobustRecSys @ RecSys2024: Design, Evaluation and Deployment of Robust Recommender Systems
RecSys '24: Proceedings of the 18th ACM Conference on Recommender SystemsPages 1265–1269https://doi.org/10.1145/3640457.3687106In recent years, recommender systems have become indispensable tools in various domains, aiding users in discovering relevant content amidst the overwhelming amount of available material. However, the effectiveness and reliability of these systems are ...
- research-articleOctober 2024
Automated Robustness Verification of Concurrent Data Structure Libraries against Relaxed Memory Models
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue OOPSLA2Article No.: 362, Pages 2578–2605https://doi.org/10.1145/3689802Clients reason about the behavior of concurrent data structure libraries such as sets, queues, or stacks using specifications that capture well-understood correctness conditions, such as linearizability. The implementation of these libraries, however, ...
- research-articleSeptember 2024
Robust tensor ring-based graph completion for incomplete multi-view clustering
AbstractIncomplete multi-view clustering (IMVC) aims to enhance clustering performance by leveraging complementary information from multi-view data, even in the presence of missing instances. This is challenging due to the interference caused by these ...
Highlights- Integrating tensor ring completion and M-estimator-based techniques into IMVC.
- Developing efficient Half-Quadratic (HQ) based iterative algorithms.
- Offering GMC penalty regularization to ensure low-rank properties.
- ...
- ArticleSeptember 2024
-
- research-articleSeptember 2024JUST ACCEPTED
Overheard: Audio-based Integral Event Inference
There is no doubt that the popularity of smart devices and the development of deep learning models bring individuals too much convenience. However, some rancorous attackers can also implement unexpected privacy inferences on sensed data from smart devices ...
Synthesizing Boxes Preconditions for Deep Neural Networks
ISSTA 2024: Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and AnalysisPages 1708–1719https://doi.org/10.1145/3650212.3680393Deep neural network (DNN) has been increasingly deployed as a key component in safety-critical systems. However, the credibility of DNN components is uncertain due to the absence of formal specifications for their data preconditions, which are essential ...
- research-articleSeptember 2024
A Robustness-Enhanced Reconstruction Based on Discontinuity Feedback Factor for High-Order Finite Volume Scheme
Journal of Scientific Computing (JSCI), Volume 101, Issue 1https://doi.org/10.1007/s10915-024-02655-6AbstractIn this paper, a robustness-enhanced reconstruction for the high-order finite volume scheme is constructed on the 2-D structured mesh, and both the high-order gas-kinetic scheme and the Lax-Friedrichs flux solver are considered to verify the ...
- articleSeptember 2024
Robustness of models addressing Information Disorder: A comprehensive review and benchmarking study
AbstractMachine learning and deep learning models are increasingly susceptible to adversarial attacks, particularly in critical areas like cybersecurity and Information Disorder. This study provides a comprehensive evaluation of model Robustness against ...
- research-articleSeptember 2024
Improving robustness with image filtering
AbstractAdversarial robustness is one of the most challenging problems in Deep Learning and Computer Vision research. State-of-the-art techniques to enforce robustness are based on Adversarial Training, a computationally costly optimization procedure. ...
- research-articleSeptember 2024
Robustness of reaction–diffusion PDEs predictor-feedback to stochastic delay perturbations
Automatica (Journal of IFAC) (AJIF), Volume 167, Issue Chttps://doi.org/10.1016/j.automatica.2024.111784AbstractThis paper studies the robustness of a PDE backstepping delay-compensated boundary controller for a reaction–diffusion partial differential equation (PDE) with respect to a nominal delay subject to stochastic error disturbance. The stabilization ...
- ArticleAugust 2024
Byzantine-Robust Aggregation for Federated Learning with Reinforcement Learning
AbstractFederated learning (FL) is a promising distributed machine learning approach that aims to address the challenges of data isolation and data privacy protection, thereby fostering the collaborative training of models and the sharing of information ...
- ArticleAugust 2024
Robust Lightweight Neural Network Architecture Search Based on Multi-objective Particle Swarm Optimization
AbstractIn recent years, lightweight neural network architectures have been improved dramatically in terms of search velocity and accuracy, but it is difficult to maintain their stability and robustness in the face of different attacks. This paper aims to ...
- ArticleAugust 2024
Constructing Robust and Influential Networks Against Cascading Failures via a Multi-objective Evolutionary Algorithm
AbstractThe influence maximization problem and robustness optimization of networks are hot-spots in the current research. Existing studies have rather investigated the problems of network robustness optimization or influence maximization separately, ...
- research-articleAugust 2024
Perceptual authentication hashing for digital images based on multi-domain feature fusion
AbstractIn recent decades, numerous perceptual authentication hashing schemes have been proposed for image content authentication. However, most of these schemes are based on a single spatial or transform domain, and they fail to provide satisfactory ...
Highlights- A new robust perceptual hashing scheme for image authentication is proposed.
- Multi-domain feature fusion strategy is exploited for hash sequence generation.
- The channel filter and attention module are designed in frequency domain.
- research-articleAugust 2024
Robust augmented Volterra adaptive filtering
Highlights- This paper proposes a new nonlinear system model for signal processing and develops its corresponding adaptive algorithm.
- This paper also gives a variant version of the proposed algorithm to reduce its complexity.
- The performance ...
In the field of nonlinear signal processing, Volterra filter is generally used as an effective tool. The utilization of the augmented model can make the filter maintain its merit in both circular and non-circular signals. From this point of view, ...
- research-articleAugust 2024
A comparative study of deep learning and iterative algorithms for joint channel estimation and signal detection in OFDM systems
AbstractJoint channel estimation and signal detection (JCESD) is crucial in orthogonal frequency division multiplexing (OFDM) systems, but traditional algorithms perform poorly in low signal-to-noise ratio (SNR) scenarios. Deep learning (DL) methods have ...
Highlights- We create a benchmark for the task of joint channel estimation and signal detection.
- Deep learning methods perform better in the more challenging low-SNR setting.
- The iterative algorithm outperforms in the high-SNR setting with ...
- research-articleAugust 2024
Proportionate affine projection tanh algorithm and its step-size optimization
AbstractThe problem of sparse adaptive system identification such as acoustic echo cancellation (AEC) needs robust adaptive filtering algorithms in the situation where the system is often corrupted by impulsive noise. To solve this problem this work ...
Highlights- This work proposes a proportionate affine projection tanh algorithm robust against impulsive noise.
- The proportionate can speed convergence rate.
- The steady-state performance and stability conditions are analyzed.
- The step-size ...
- research-articleAugust 2024
Robust graph embedding via Attack-aid Graph Denoising
Information Sciences: an International Journal (ISCI), Volume 678, Issue Chttps://doi.org/10.1016/j.ins.2024.120942AbstractThe quality of graphs directly affects the result of graph embedding since most existing models are vulnerable and highly sensitive to harmful/missing edges and imperceptible attacks. In this study, we propose a new robust graph embedding ...
Highlights- Proposed Attack-aid Graph Denoising improves the graph quality and robustness.
- AGD enhances robustness by leveraging auxiliary attacks for edge manipulation.
- Proposed Topology Knowledge Extraction adapts message-passing to isolate ...